CVE-2026-47391

Summary

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a calculate(expression) tool implemented with Python eval(). The example also binds to 0.0.0.0. A remote unauthenticated attacker can send message/send to /a2a; the request reaches agent.chat(), and a real LLM can invoke the registered calculate tool. In testing with gemini/gemini-2.5-flash-lite, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.

Affected Software

VendorProductVersion RangeStatus
MervinPraisonPraisonAI< 4.6.40affected

Weaknesses

  • CWE-95: CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
  • CWE-306: CWE-306: Missing Authentication for Critical Function

References